skills.rest
teradata-labs
teradata-labsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

td-ngram-splitter

Generate unigrams, bigrams, and trigrams from text using Teradata Vantage.

7|Updated Dec 3, 2025
Search Tags:#nlp#preprocessing#ngram#teradata#text analytics#td_ngramsplitter
One-click install
npx skills add https://github.com/teradata-labs/claude-cookbooks --skill td-ngram-splitter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: td-ngram-splitter
Source: https://github.com/teradata-labs/claude-cookbooks/tree/main/skills/analytics/td-ngram-splitter
Command: npx skills add https://github.com/teradata-labs/claude-cookbooks --skill td-ngram-splitter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and resources (resource) components.

What problem does it solve?

This skill automates the process of generating n-grams from text data, which is a crucial step in many natural language processing tasks like text analysis and language modeling.

Core Features & Use Cases

  • N-gram Generation: Creates unigrams, bigrams, and trigrams from text.
  • Text Preprocessing: Cleans and prepares text data for analysis.
  • Use Case: Analyze customer reviews to identify common phrases (bigrams) or keywords (unigrams) that indicate product sentiment.

Quick Start

Use the td-ngram-splitter skill to generate n-grams from the 'customer_feedback' table.

Frequently Asked Questions about td-ngram-splitter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate n-grams for text analytics in Teradata Vantage?▼

You can generate n-grams in Teradata Vantage by using the TD_Ngramsplitter function to process text data, creating unigrams, bigrams, and trigrams directly within the database for language modeling and text analysis workflows.

Can I extract bigrams from customer review text for sentiment analysis?▼

Yes, you can extract bigrams from customer reviews. The n-gram generation process tokenizes and cleans text data, isolating common phrases and keywords that indicate product sentiment for downstream analysis.

What do I need to run n-gram generation on my text data?▼

You need a Teradata Vantage environment with ClearScape Analytics enabled and appropriate database permissions to access and execute the TD_Ngramsplitter function on your target text tables.

Does n-gram generation support text preprocessing and tokenization?▼

Yes, n-gram generation includes text preprocessing capabilities. It cleans and prepares raw text data by tokenizing the input before creating the unigrams, bigrams, and trigrams needed for analysis.

Why use in-database n-gram generation instead of extracting text for external processing?▼

In-database n-gram generation leverages Teradata Vantage's processing power, avoiding the data movement overhead of external extraction while securely preparing text tokens for large-scale language modeling workflows.

Related Skills

Explore More Data & Analytics Skills→
teradata-labsteradata-labs
7

td-kmeans

Perform K-means clustering on Teradata Vantage tables using TD_KMeans.

Official
Advanced
PatkikPatkik

content-analysis

Extract sentiment, topics, keywords, and insights from text content.

Community
Intermediate
teradata-labsteradata-labs
7

td-tfidf

Generate TF-IDF scores and features from Teradata text data using TD_TFIDF.

Official
Advanced
qcmuuqcmuu

sentencepiece

Train language-independent subword tokenizers for multilingual NLP pipelines.

Community
Intermediate